Anthony Damico ajdamico

## maximal legal time difference.R
    library(lubridate)

    x <- ymd_h( "1999-12-31:23" )
    y <- ymd_h( "2000-01-02:01" )

    # https://en.wikipedia.org/wiki/UTC%E2%88%9212:00
    ( x1 <- force_tzs( x , tzone="Etc/GMT+12" , tzone_out="UTC" ) )
    # https://en.wikipedia.org/wiki/UTC%2B14:00
    ( y1 <- force_tzs( y , tzone="Pacific/Kiritimati" , tzone_out="UTC" ) )
    difftime( x1 , y1 )

## baby name crown years and places.R
tf <- tempfile()
download.file( "https://www.ssa.gov/oact/babynames/state/namesbystate.zip" , tf , mode = 'wb' )
z <- unzip( tf , exdir = tempdir() )
state_files <- grep( "\\.TXT$" , z , value = TRUE )
state_list <- lapply( state_files , read.table , header = FALSE , sep = ',' , stringsAsFactors = FALSE )
w <- do.call(rbind,state_list)
names( w ) <- c( 'stateab' , 'sex' , 'year' , 'name' , 'count' )
maxes <- with( w , tapply( count , list( year , stateab , sex ) , max ) )
max_df <- reshape2::melt( maxes )
names( max_df ) <- c( 'year' , 'stateab' , 'sex' , 'count' )

## district of columbia craigslist job postings by day in march.R
library(rvest)

baseurl <- "https://washingtondc.craigslist.org/search/doc/jjj"

raw_query_list <-
	lapply(
		paste0( baseurl , "?s=" , seq( 0 , 1469 , 120 ) ) ,
		xml2::read_html
	)

## download all files from an FTP site.R
#install RCurl on your version of R if you don't already have it
#just run this once
#install.packages("RCurl")

#program start
#load the RCurl package
library(RCurl)

#set your output folder - this is where the pdfs will get saved
setwd("R:/National Health Interview Survey/documentation")

## download the medical expenditure panel survey.R
library(RCurl)

setwd("R:\\Medical Expenditure Panel Survey\\Data")

#input all available MEPS public use file numbers
year <- c(1996:2008)
consolidated <- c(12,20,28,38,50,60,70,79,89,97,105,113,NA)
conditions <- c("06r",18,27,37,52,61,69,78,87,96,104,112,NA)
jobs <- c("07",19,25,32,40,56,63,74,83,91,100,108,116)
prpf <- c(24,47,47,47,47,57,66,76,88,95,103,111,119)

## NHIS download matrix.R

#load necessary libraries
library(stringr)
library(foreign)
library(survey)
library(RCurl)

#set the temporary directory to download all files to!
setwd("s:/temp")

## survey design subsetting.R
library(survey)

data(api)

x <- apistrat

x <- subset( x , comp.imp == 'Yes' )

dstrat_before<-svydesign(id=~1,strata=~stype, weights=~pw, data=x, fpc=~fpc)

## machine learning foundations


# support vector machines #
data(quakes)
plot( quakes , col = as.factor( round( quakes$mag ) ) )

this_df <- quakes
this_df[ , 'mag' ] <- as.factor( round( this_df[ , 'mag' ] ) )

library(e1071)

## convey flowchart.mmd

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                ajdamico
                / convey flowchart.mmd
            
            
              Created
              September 13, 2023 17:25
            
              
                convey flowchart
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## using R to replicate the NHIS Multiple Imputation technique.R
#page 118 of the NHIS document
#ftp://ftp.cdc.gov/pub/health_statistics/nchs/dataset_documentation/nhis/2010/srvydesc.pdf
#displays the R code to load the persons file into R as a survey object
#the code below creates a slightly different survey object, one that includes appropriately-imputed income.


#this R code:
#	reads the year 2000 personsx file into R
#	reads in all five imputed income files
#	merges the 2000 personsx file with the five imputed income files
	library(lubridate)

	x <- ymd_h( "1999-12-31:23" )
	y <- ymd_h( "2000-01-02:01" )

	# https://en.wikipedia.org/wiki/UTC%E2%88%9212:00
	( x1 <- force_tzs( x , tzone="Etc/GMT+12" , tzone_out="UTC" ) )
	# https://en.wikipedia.org/wiki/UTC%2B14:00
	( y1 <- force_tzs( y , tzone="Pacific/Kiritimati" , tzone_out="UTC" ) )
	difftime( x1 , y1 )
	tf <- tempfile()
	download.file( "https://www.ssa.gov/oact/babynames/state/namesbystate.zip" , tf , mode = 'wb' )
	z <- unzip( tf , exdir = tempdir() )
	state_files <- grep( "\\.TXT$" , z , value = TRUE )
	state_list <- lapply( state_files , read.table , header = FALSE , sep = ',' , stringsAsFactors = FALSE )
	w <- do.call(rbind,state_list)
	names( w ) <- c( 'stateab' , 'sex' , 'year' , 'name' , 'count' )
	maxes <- with( w , tapply( count , list( year , stateab , sex ) , max ) )
	max_df <- reshape2::melt( maxes )
	names( max_df ) <- c( 'year' , 'stateab' , 'sex' , 'count' )
	library(rvest)

	baseurl <- "https://washingtondc.craigslist.org/search/doc/jjj"

	raw_query_list <-
	lapply(
	paste0( baseurl , "?s=" , seq( 0 , 1469 , 120 ) ) ,
	xml2::read_html
	)
	#install RCurl on your version of R if you don't already have it
	#just run this once
	#install.packages("RCurl")

	#program start
	#load the RCurl package
	library(RCurl)

	#set your output folder - this is where the pdfs will get saved
	setwd("R:/National Health Interview Survey/documentation")
	library(RCurl)

	setwd("R:\\Medical Expenditure Panel Survey\\Data")

	#input all available MEPS public use file numbers
	year <- c(1996:2008)
	consolidated <- c(12,20,28,38,50,60,70,79,89,97,105,113,NA)
	conditions <- c("06r",18,27,37,52,61,69,78,87,96,104,112,NA)
	jobs <- c("07",19,25,32,40,56,63,74,83,91,100,108,116)
	prpf <- c(24,47,47,47,47,57,66,76,88,95,103,111,119)

	#load necessary libraries
	library(stringr)
	library(foreign)
	library(survey)
	library(RCurl)

	#set the temporary directory to download all files to!
	setwd("s:/temp")
	library(survey)

	data(api)

	x <- apistrat

	x <- subset( x , comp.imp == 'Yes' )

	dstrat_before<-svydesign(id=~1,strata=~stype, weights=~pw, data=x, fpc=~fpc)


	# support vector machines #
	data(quakes)
	plot( quakes , col = as.factor( round( quakes$mag ) ) )

	this_df <- quakes
	this_df[ , 'mag' ] <- as.factor( round( this_df[ , 'mag' ] ) )

	library(e1071)
	#page 118 of the NHIS document
	#ftp://ftp.cdc.gov/pub/health_statistics/nchs/dataset_documentation/nhis/2010/srvydesc.pdf
	#displays the R code to load the persons file into R as a survey object
	#the code below creates a slightly different survey object, one that includes appropriately-imputed income.


	#this R code:
	# reads the year 2000 personsx file into R
	# reads in all five imputed income files
	# merges the 2000 personsx file with the five imputed income files